Unsupervised Lexicon Discovery from Acoustic Input
We present a model of unsupervised phonological lexicon discovery -- the problem of simultaneously learning phoneme-like and word-like units from acoustic input. Our model builds on earlier models of unsupervised phone-like unit discovery from acoustic data (Lee and Glass, 2012), and unsupervised sy...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | en_US |
Published: |
Association for Computational Linguistics
2015
|
Online Access: | http://hdl.handle.net/1721.1/98523 https://orcid.org/0000-0002-3097-360X https://orcid.org/0000-0002-5711-977X |
_version_ | 1811094966909272064 |
---|---|
author | Lee, Chia-ying O'Donnell, Timothy John Glass, James R. |
author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Lee, Chia-ying O'Donnell, Timothy John Glass, James R. |
author_sort | Lee, Chia-ying |
collection | MIT |
description | We present a model of unsupervised phonological lexicon discovery -- the problem of simultaneously learning phoneme-like and word-like units from acoustic input. Our model builds on earlier models of unsupervised phone-like unit discovery from acoustic data (Lee and Glass, 2012), and unsupervised symbolic lexicon discovery using the Adaptor Grammar framework (Johnson et al., 2006), integrating these earlier approaches using a probabilistic model of phonological variation. We show that the model is competitive with state-of-the-art spoken term discovery systems, and present analyses exploring the model's behavior and the kinds of linguistic structures it learns. |
first_indexed | 2024-09-23T16:08:23Z |
format | Article |
id | mit-1721.1/98523 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T16:08:23Z |
publishDate | 2015 |
publisher | Association for Computational Linguistics |
record_format | dspace |
spelling | mit-1721.1/985232022-09-29T18:27:16Z Unsupervised Lexicon Discovery from Acoustic Input Lee, Chia-ying O'Donnell, Timothy John Glass, James R. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences Lee, Chia-ying O'Donnell, Timothy John Glass, James R. We present a model of unsupervised phonological lexicon discovery -- the problem of simultaneously learning phoneme-like and word-like units from acoustic input. Our model builds on earlier models of unsupervised phone-like unit discovery from acoustic data (Lee and Glass, 2012), and unsupervised symbolic lexicon discovery using the Adaptor Grammar framework (Johnson et al., 2006), integrating these earlier approaches using a probabilistic model of phonological variation. We show that the model is competitive with state-of-the-art spoken term discovery systems, and present analyses exploring the model's behavior and the kinds of linguistic structures it learns. 2015-09-16T11:39:37Z 2015-09-16T11:39:37Z 2015-07 2015-02 Article http://purl.org/eprint/type/JournalArticle 2307-387X http://hdl.handle.net/1721.1/98523 Lee, Chia-ying, Timothy J. O'Donnell, and James Glass. "Unsupervised Lexicon Discovery from Acoustic Input." Transactions of the Association for Computational Linguistics, Volume 3 (2015). © 2015 Association for Computational Linguistics https://orcid.org/0000-0002-3097-360X https://orcid.org/0000-0002-5711-977X en_US https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/520 Transactions of the Association for Computational Linguistics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Association for Computational Linguistics Transactions of the Association for Computational Linguistics |
spellingShingle | Lee, Chia-ying O'Donnell, Timothy John Glass, James R. Unsupervised Lexicon Discovery from Acoustic Input |
title | Unsupervised Lexicon Discovery from Acoustic Input |
title_full | Unsupervised Lexicon Discovery from Acoustic Input |
title_fullStr | Unsupervised Lexicon Discovery from Acoustic Input |
title_full_unstemmed | Unsupervised Lexicon Discovery from Acoustic Input |
title_short | Unsupervised Lexicon Discovery from Acoustic Input |
title_sort | unsupervised lexicon discovery from acoustic input |
url | http://hdl.handle.net/1721.1/98523 https://orcid.org/0000-0002-3097-360X https://orcid.org/0000-0002-5711-977X |
work_keys_str_mv | AT leechiaying unsupervisedlexicondiscoveryfromacousticinput AT odonnelltimothyjohn unsupervisedlexicondiscoveryfromacousticinput AT glassjamesr unsupervisedlexicondiscoveryfromacousticinput |